DeepSeek-V4-Pro-0813

DeepSeek

Copy success!

Try AIAdd to Compare

Overview

A flagship Mixture-of-Experts (MoE) large language model with 1.6 trillion total parameters and 49 billion activated parameters. It natively supports context windows of up to 1 million tokens. Trained on extensive high-quality data, the model delivers strong performance in mathematical and logical reasoning, complex reasoning, professional code generation, and in-depth long-document analysis, and is suitable for demanding scenarios such as advanced scientific research, complex enterprise workflows, and sophisticated agentic applications.

Input

Text

Output

Text

Features

Prefix Completion

Enable Partial Mode when calling the Qwen API to make the model continue strictly from your provided prefix text.View docs

Function Calling

Use function calling to connect large language models with external tools and systems.View docs

Cache

Context Cache stores shared prefixes for long-context requests to reduce repeated computation, improve latency, and lower cost.View docs

Structured Outputs

Structured Outputs help ensure the model returns a JSON string in the expected format.View docs

Batches

Asynchronously process requests in batches to reduce costs.View docs

Web Search

Enable web search so the model can answer with real-time retrieved data.View docs

Fine-tuning

Train models on sample data to better adapt them to specific tasks.View docs

Pricing

Input
$0.66Per 1M tokens
Input
$1.32Per 1M tokens
Output
$1.98Per 1M tokens
Output
$3.96Per 1M tokens
Input(Implicit Cache)
$0.066Per 1M tokens
Input(Implicit Cache)
$0.132Per 1M tokens

Rate Limits & Context

Max Input
1M
Max Output
393K
Max Input (Thinking)
1M
Max Output (Thinking)
393K
Context
1M
Max Reasoning
393K
TPMTokens Per Minute
1M
RPMRequests Per Minute
10K

Built-in Tools

code_interpreterResponses API

web_extractorResponses API

web_searchResponses API

API Reference

Call API

Copy success!

123456789101112131415161718192021222324252627282930

from openai import OpenAI
import os

client = OpenAI(
    # If the environment variable is not set, replace it with your Model Studio API key: api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)

messages = [{"role": "user", "content": "Who are you"}]
completion = client.chat.completions.create(
    model="deepseek-v4-pro-0813",  # You can replace this with another deep thinking models
    messages=messages,
    extra_body={"enable_thinking": True},
    stream=True
)
is_answering = False  # Indicates whether the response phase has started
print("\n" + "=" * 20 + "Thinking process" + "=" * 20)
for chunk in completion:
    if not chunk.choices:
        continue
    delta = chunk.choices[0].delta
    if hasattr(delta, "reasoning_content") and delta.reasoning_content is not None:
        if not is_answering:
            print(delta.reasoning_content, end="", flush=True)
    if hasattr(delta, "content") and delta.content:
        if not is_answering:
            print("\n" + "=" * 20 + "Full response" + "=" * 20)
            is_answering = True
        print(delta.content, end="", flush=True)